The study presents a framework for online power system dynamic stability enhancement with a new market-based rescheduling approach. The objective is to solve the online transient and oscillatory stability constrained economic power dispatch problem using a mixture of a modified particle swarm optimisation (PSO) and artificial neural network. The problem is formulated as a non-linear constrained optimisation problem, and PSO has been used as optimisation tool to search for the optimal solution within the available hyperspace. For reducing the time consumed in the computations, neural network has been used to assess power system dynamic stability. The rescheduling process based on the market participants' bids is used as a remedial action to maintain system operation sufficiently away from the limits of system stability. The goal of the approach is to minimise the additional payments arising from the rescheduling needed to enhance system dynamic stability. The critical clearing time corresponding to the critical contingency is considered as an index for transient stability, while system minimum damping of oscillation is considered as an indicator for oscillatory stability. The proposed framework is implemented on a 66-bus test system, and the results obtained are found to be satisfactory.